© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 1782
    Prev
    Next
    INDEX
    Explanations

    calling out hypocrisy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    1.30
    ,—
    1.22
    ;:
    1.18
     एवं
    1.13
    
    1.13
    いたします
    1.05
    !;
    1.04
    ;,
    1.03
    ﹔
    1.01
    ؛
    1.01
    POSITIVE LOGITS
     shitty
    2.08
     idk
    2.06
     ppl
    1.98
     kinda
    1.83
     tiktok
    1.83
    めっちゃ
    1.76
     disgusting
    1.74
     covid
    1.70
     fuck
    1.70
     đc
    1.70
    Activations Density 0.058%

    No Known Activations